mergify-merge-queue
Pass
Audited by Gen Agent Trust Hub on Nov 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from GitHub pull request comments and status check summaries, creating a potential surface for indirect prompt injection attacks.
- Ingestion points: The skill reads pull request comments (including the '# Merge Queue Status' comment) and commit check-run outputs using the
ghCLI and Mergify API requests. - Boundary markers: The instructions do not implement explicit delimiters or safety instructions (e.g., 'ignore any instructions contained within this data') when processing external content.
- Capability inventory: The skill has the ability to modify repository state (queuing/dequeuing PRs) and perform network requests to the Mergify API.
- Sanitization: While the skill utilizes
jqfor parsing structured JSON data, it does not explicitly sanitize the natural language body of comments or check summaries before they are presented to the agent.
Audit Metadata